# Medico: Towards Hallucination Detection and Correction with Multi-source Evidence Fusion

arXiv: https://arxiv.org/abs/2410.10408 · HTML: https://mlsanity.com/paper/2410.10408/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 40 references that are in the map.
- First posted on arXiv 14 Oct 2024.

## Builds on (most cited first, 24 of 24)

- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [On Faithfulness and Factuality in Abstractive Summarization](https://mlsanity.com/paper/2005.00661/) (2020)
- [A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity](https://mlsanity.com/paper/2302.04023/) (2023)
- [A Survey on In-context Learning](https://mlsanity.com/paper/2301.00234/) (2022)
- [Retrieval Augmentation Reduces Hallucination in Conversation](https://mlsanity.com/paper/2104.07567/) (2021)
- [Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment](https://mlsanity.com/paper/2308.05374/) (2023)
- [KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation](https://mlsanity.com/paper/1911.06136/) (2019)
- [RARR: Researching and Revising What Language Models Say, Using Language Models](https://mlsanity.com/paper/2210.08726/) (2022)
- [FacTool: Factuality Detection in Generative AI -- A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarios](https://mlsanity.com/paper/2307.13528/) (2023)
- [Gradio: Hassle-Free Sharing and Testing of ML Models in the Wild](https://mlsanity.com/paper/1906.02569/) (2019)
- [Long-form factuality in large language models](https://mlsanity.com/paper/2403.18802/) (2024)
- [Hallucinated but Factual! Inspecting the Factuality of Hallucinations in Abstractive Summarization](https://mlsanity.com/paper/2109.09784/) (2021)
- [Hallucinations in Large Multilingual Translation Models](https://mlsanity.com/paper/2303.16104/) (2023)
- [Factual Error Correction for Abstractive Summarization Models](https://mlsanity.com/paper/2010.08712/) (2020)
- [Do LLMs Know about Hallucination? An Empirical Investigation of LLM's Hidden States](https://mlsanity.com/paper/2402.09733/) (2024)
- [Evidence-based Factual Error Correction](https://mlsanity.com/paper/2012.15788/) (2020)
- [FRUIT: Faithfully Reflecting Updated Information in Text](https://mlsanity.com/paper/2112.08634/) (2021)
- [Correcting Diverse Factual Errors in Abstractive Summarization via Post-Editing and Language Model Infilling](https://mlsanity.com/paper/2210.12378/) (2022)
- [FactLLaMA: Optimizing Instruction-Following Language Models with External Knowledge for Automated Fact-Checking](https://mlsanity.com/paper/2309.00240/) (2023)
- [Automatic Fact-guided Sentence Modification](https://mlsanity.com/paper/1909.13838/) (2019)
- [FLEEK: Factual Error Detection and Correction with Evidence Retrieved from External Knowledge](https://mlsanity.com/paper/2310.17119/) (2023)
- [Fact-based Text Editing](https://mlsanity.com/paper/2007.00916/) (2020)

## Built on by (most cited first, 3 of 3)

- [Hallucination to Truth: A Review of Fact-Checking and Factuality Evaluation in Large Language Models](https://mlsanity.com/paper/2508.03860/) (2025)
- [Learning to Extract Rational Evidence via Reinforcement Learning for Retrieval-Augmented Generation](https://mlsanity.com/paper/2507.15586/) (2025)
- [SeaPO: Strategic Error Amplification for Robust Preference Optimization of Large Language Models](https://mlsanity.com/paper/2509.24781/) (2025)

## Abstract (arXiv)

As we all know, hallucinations prevail in Large Language Models (LLMs), where the generated content is coherent but factually incorrect, which inflicts a heavy blow on the widespread application of LLMs. Previous studies have shown that LLMs could confidently state non-existent facts rather than answering ``I don't know''. Therefore, it is necessary to resort to external knowledge to detect and correct the hallucinated content. Since manual detection and correction of factual errors is labor-intensive, developing an automatic end-to-end hallucination-checking approach is indeed a needful thing. To this end, we present Medico, a Multi-source evidence fusion enhanced hallucination detection and correction framework. It fuses diverse evidence from multiple sources, detects whether the generated content contains factual errors, provides the rationale behind the judgment, and iteratively revises the hallucinated content. Experimental results on evidence retrieval (0.964 HR@5, 0.908 MRR@5), hallucination detection (0.927-0.951 F1), and hallucination correction (0.973-0.979 approval rate) manifest the great potential of Medico. A video demo of Medico can be found at https://youtu.be/RtsO6CSesBI.